Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 3 models | liquidLiquidAI: d1-ultraRemove × | togethercomputerTogether: Tev1 4B ExperimentalRemove × | nace-aiNace.AI: Drex v2.0Remove × |
|---|---|---|---|
| What’s different | d1-ultra is Liquid AI's largest decision model, served as a System One endpoint. Send a state of text and images along with typed questions, and it returns a choice, a... | Tev1 4B Experimental is an experimental decision model from Together AI, a supervised fine-tune of Qwen3.5-4B trained to choose one option from a structured state, question, and list of 2-24... | Self-hosted decision scoring via Python or dedicated llama.cpp/Ollama forks; returns option probabilities without prose. |
| Date | Oct 15, 2026Listed | Sep 30, 2026Listed | Oct 12, 2026Listed |
API prices USD · provider configuration shown below | |||
| Listed rate | $0.042 in / $0.00 out/ 1M tokensOpenRouter · all routes ↗ | $0.042 in / $0.00 out/ 1M tokensOpenRouter · all routes ↗ | $0.06 in / $0.00 out/ 1M tokensOpenRouter · all routes ↗ |
| Provider endpoints | 1 endpoint → | 1 endpoint → | 1 endpoint → |
Specifications | |||
| Context window | 32.8K | 32.8K | 131.1K |
| Max output | 29.5K | 8 | 118K |
| Parameters | — | 4B | — |
| Image input | Supported | Not reported | Not reported |
| Prompt caching | Supported | Not reported | Not reported |
| Open weights | Not reported | Supported | Not reported |